Yankees right-hander Clay Holmes has had a roller-coaster season. After nailing down the save in Sunday’s game against Texas, Holmes has 25 saves and is tied with Josh Hader of the Astros and Robert Suarez of the Padres for 4th in the MLB. Holmes, however, leads MLB with 9 blown saves. The next highest number of blown saves by one of MLB’s top closers is just 4, by the Nationals Kyle Finnegan.

Should Holmes be the Yankees closer? In this analysis, I'll examine Holmes' distribution of runs allowed, compare it to the league average, and assess whether he is well-suited for the closer role.

Photo Credit: AP Photo/Adam Hunger

Consider this scenario: Two players each have 30 base steals and 5 bases caught stealing. With an 86% success rate, both players appear to be helping their teams significantly by risking taking the extra base. However, 35 attempts is quite a small sample size. The standard deviation of the number of stolen bases in this case is 2.07. So, there’s a 2.5% chance that the base-stealer’s true success rate is actually lower than 74%, in which case the advice to that player would be to steal fewer bases. Essentially, for many players, it can be hard to tell If they should steal more or less, purely based on their stolen bases and caught stealing, since the sample sizes are small.

What if we had a metric that would give us even more confidence in telling the players to steal more frequently?

Photo Credit: John Fisher/Getty Images